Learning A Single Network for Scale-Arbitrary Super-Resolution
Longguang Wang, Yingqian Wang, Zaiping Lin, Jungang Yang, Wei An, Yulan Guo
National University of Defense Technology
Abstract
Recently, the performance of single image super-resolution (SR) has been significantly improved with powerful networks. However, these networks are developed for image SR with specific integer scale factors (x2/3/4), and cannot handle non-integer and asymmetric SR. In this paper, we propose to learn a scale-arbitrary image SR network from scale-specific networks. Specifically, we develop a plug-in module for existing SR networks to perform scale-arbitrary SR, which consists of multiple scale-aware feature adaption blocks and a scale-aware upsampling layer. Moreover, conditional convolution is used in our plug-in module to generate dynamic scale-aware filters, which enables our network to adapt to arbitrary scale factors. Our plug-in module can be easily adapted to existing networks to realize scale-arbitrary SR with a single model. These networks plugged with our module can produce promising results for non-integer and asymmetric SR while maintaining state-of-the-art performance for SR with integer scale factors. Besides, the additional computational and memory cost of our module is very small.
Network Architecture
Figure 1. An overview of our plug-in module.
Figure 2. An illustration of our scale-aware feature adaption block (a) and scale-aware upsampling layer.
Results
(1) SR with Symmetric Scale Factors
(2) SR with Asymmetric Scale Factors
(3) SR with Continuous Scale Factors
Materials
Citation
@InProceedings{Wang2021Learning,
author = {Wang, Longguang and Wang, Yingqian and Lin, Zaiping and Yang, Jungang and An, Wei and Guo, Yulan},
title = {Learning A Single Network for Scale-Arbitrary Super-Resolution},
booktitle = {ICCV},
year = {2021}}
Contact